6 accepted papers
As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on *post-hoc mitigation*---especially machine unlearning and inference-time guardrails---to argue for compliance. **This paper argues that such post-hoc mitigation methods cannot retroactivel…
We present UniDetox, a universally applicable method designed to mitigate toxicity across various large language models (LLMs). Previous detoxification methods are typically model-specific, addressing only individual models or model families, and require careful hyperparameter tuning due to the trad…
Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks. Although various types of instructions have been manually created for instruction tuning, it is still unclear what kind of instruction is optimal to obtain cross-task generalizatio…
This study presents a dynamic structured neural topic model, which can handle the time-series development of topics while capturing their dependencies. Our model captures the topic branching and merging processes by modeling topic dependencies based on a self-attention mechanism. Additionally, we in…
Automatic literature review generation is one of the most challenging tasks in natural language processing. Although large language models have tackled literature review generation, the absence of large-scale datasets has been a stumbling block to the progress. We release SciReviewGen, consisting of…
In this paper, we introduce a novel method for lexical entailment tasks, which detects a hyponym-hypernym relation among words. Existing lexical entailment studies are lacking in generalization performance, as they cannot be applied to words that are not included in the training dataset. Moreover, e…